Skip to main content
Glama

TOISE — intelligence foncière

Friches recensées autour d’un lieu

toise_friches
Read-onlyIdempotent

Où sont les friches d'une commune ou autour d'une adresse : sites, surface, zonage, pollution (Cartofriches). Adresse ou lat/lon + rayon_m, code_insee ou département ; plus de 1 ha par défaut. « Potentielle » = repérage automatique ; propriétaire à recouper avec toise_proprietaire. Source Cartofriches.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "toise_friches"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNo
lonNo
typeNoType de friche tel que publié par…
limiteNo
statutNoStatut de la friche. Facultatif.
adresseNo
curseurNo
rayon_mNo
code_inseeNo
departementNo
surface_min_m2NoSurface minimale en m²…

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
sitesYes
totalYesSites correspondants lus…
centreNoPoint de recherche { lat, lon, adresse_retenue } ; null en…
curseurYes
partielNotrue : une source n’a pas répondu, des champs manquent…
rayon_mNo
sourcesYes
has_moreYes
visiteurNoNon nul sans compte : aperçu plafonné, avec motif.
warningsYes
perimetreYes
retournesYes
vide_motifNoPrésent quand aucun site : pourquoi ce vide ne prouve pas…
total_exactYesVrai si la lecture est complète ; sinon total est un…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
champs_absentsNoDonnées absentes du résultat partiel.
surface_min_m2No
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
limite_appliqueeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / type / description
      Previous value: -"Type de friche tel que publié par Cartofriches…"New value: +"Type de friche tel que publié par…"
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds the data provenance (Cartofriches) and the important data-quality caveat that « Potentielle » means automatic detection rather than a verified state. It also discloses an implicit default filter (1 ha) that would otherwise silently change results. Return-shape detail is left to the output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Information is front-loaded: purpose first, then accepted inputs, then the default threshold, then the data caveat and sibling pointer. Dense semicolon-separated clauses keep it short, though the packing makes it slightly harder to scan than a cleanly bulleted equivalent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no prose, and the description covers the search modes, default filter, and data caveats appropriate for a read-only search tool. The remaining gap is pagination behavior for an 11-parameter, potentially large result set, which an agent must infer from parameter names alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 11 parameters and only 27% schema description coverage, the description must compensate; it does explain the geography parameters and the implicit surface_min_m2 default, plus the meaning of the statut value « potentielle ». However, the pagination parameters (limite, curseur) and the `type` filter are never mentioned, leaving several parameters undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with the exact question the tool answers ("Où sont les friches d'une commune ou autour d'une adresse") and enumerates the returned content (sites, surface, zonage, pollution) with the source (Cartofriches). It also draws a boundary against the sibling toise_proprietaire, which is where owner information must be looked up.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the accepted location inputs (adresse OR lat/lon + rayon_m, code_insee OR département) and the default behavior of filtering above 1 ha, which is real when-to-use context. It also explicitly routes the agent to toise_proprietaire for ownership rather than trying to get it here. No explicit exclusion or 'do not use for X' statement, so not a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources